Remove existing models

.user.yml

@@ -0,0 +1 @@
+id: a6084397-071e-43eb-8cb1-12d7e277cae5

dbt_project.yml

@@ -1,7 +1,7 @@
 name: 'jaffle_shop'
 
 config-version: 2
-version: '0.1'
+version: '1.5.0'
 
 profile: 'jaffle_shop'
 
@@ -13,14 +13,25 @@ macro-paths: ["macros"]
 
 target-path: "target"
 clean-targets:
-    - "target"
-    - "dbt_modules"
-    - "logs"
+  - "target"
+  - "dbt_modules"
+  - "logs"
 
 require-dbt-version: [">=1.0.0", "<2.0.0"]
 
 models:
   jaffle_shop:
-      materialized: table
-      staging:
-        materialized: view
+    # Default materialization for the project
+    +materialized: table
+
+    staging:
+      +materialized: view  # All models in the staging folder will be views by default
+
+    marts:
+      # Default materialization for marts folder
+      +materialized: table
+
+      core:
+        +schema: core  # Models in the marts/core folder will use the "core" schema
+        intermediate:
+          +schema: core_intermediate  # Models in marts/core/intermediate use "core_intermediate"

profiles.yml

@@ -0,0 +1,11 @@
+jaffle_shop:
+  target: dev
+  outputs:
+    dev:
+      type: sqlite
+      threads: 1
+      database: issues
+      schema: main
+      schema_directory: /Users/bonafide/Downloads/GitHub/fleetio/jaffle-shop-classic/scripts/data
+      schemas_and_paths:
+        main: /Users/bonafide/Downloads/GitHub/fleetio/jaffle-shop-classic/scripts/data

scripts/fetch_google_sheets.py

@@ -0,0 +1,51 @@
+import os
+import requests
+import pandas as pd
+
+# Google Sheets API setup
+API_KEY = "AIzaSyAJ7jxaWNSGsNetM9DMiMpK_h7kcS2RCNQ"  # Replace with your API key
+SPREADSHEET_ID = "1MGVed0Psao7WwIulcrASyjw_nvHslvLhuvBiKqXYmuI"  # Replace with your Google Sheet ID
+RANGE_NAME = "issues!A:N"  # Adjust range as needed
+
+# Build the URL
+url = f"https://sheets.googleapis.com/v4/spreadsheets/{SPREADSHEET_ID}/values/{RANGE_NAME}?key={API_KEY}"
+print(f"Fetching data from Google Sheets: {url}")
+
+# Fetch data
+response = requests.get(url)
+
+print(f"Response status code: {response.status_code}")
+
+if response.status_code == 200:
+    data = response.json()
+    print("Data fetched successfully from Google Sheets")
+
+    values = data.get("values", [])
+    print(f"Number of rows fetched: {len(values)}")
+
+    # Convert to DataFrame
+    if values:
+        print("Converting data to DataFrame...")
+        df = pd.DataFrame(values[1:], columns=values[0])  # Use first row as column names
+        print(f"DataFrame created with {df.shape[0]} rows and {df.shape[1]} columns")
+
+        script_dir = os.path.dirname(os.path.abspath(__file__))  # Get the directory of the current script
+        project_root = os.path.abspath(os.path.join(script_dir, '..'))  # Move one level up to `jaffle-shop-classic`
+        output_dir = os.path.join(project_root, 'data')  # Create the `data` folder inside `jaffle-shop-classic'
+        os.makedirs(output_dir, exist_ok=True)
+        output_file = os.path.join(output_dir, 'issues.csv')
+
+        # Save data to CSV
+        print(f"Saving data to {output_file}...")
+        df.to_csv(output_file, index=False)
+        print(f"Data saved to {output_file}")
+    else:
+        print("No data found.")
+else:
+    print(f"Failed to fetch data: {response.status_code}")
+    if response.status_code == 403:
+        print("Permission denied: Ensure the sheet is publicly accessible or the API key has proper access.")
+    elif response.status_code == 404:
+        print("Sheet not found: Check the SPREADSHEET_ID and ensure the sheet exists.")
+    else:
+        print(response.text)

scripts/load_to_sqlite.py

@@ -0,0 +1,33 @@
+import sqlite3
+import pandas as pd
+
+# Load CSV data
+csv_file = 'data/issues.csv'
+df = pd.read_csv(csv_file)
+
+# Debugging: Print column names
+print("Columns in CSV:", df.columns)
+
+# Connect to SQLite database (creates database if it doesn't exist)
+conn = sqlite3.connect('data/issues.db')
+cursor = conn.cursor()
+
+# Drop the table if it exists
+cursor.execute("DROP TABLE IF EXISTS issues")
+
+# Dynamically create a table with columns matching the CSV
+columns = ", ".join([f'"{col}" TEXT' for col in df.columns])  # Define all columns as TEXT
+create_table_query = f"CREATE TABLE issues ({columns});"
+cursor.execute(create_table_query)
+
+# Insert data into the table
+for _, row in df.iterrows():
+    placeholders = ", ".join(["?"] * len(row))  # Generate placeholders for all columns
+    insert_query = f"INSERT INTO issues VALUES ({placeholders})"
+    cursor.execute(insert_query, tuple(row))
+
+# Commit changes and close the connection
+conn.commit()
+conn.close()
+
+print("Data successfully loaded into SQLite database (data/issues.db).")